The project team will work on extracting key concepts from scholarly publications and explore techniques for building a taxonomy of extracted concepts by leveraging open knowledge bases (e.g., Wikipedia). The outcome of this process will be evaluated for various science and technology knowledge platform-based analysis services. The techniques, which reduce semantic ambiguity, will analyze…

Catastrophic events such as Fukushima and Katrina have made it clear that integrating physical and social causes of failure into a cohesive modeling framework is critical in order to prevent complex technological accidents and to maintain public safety and health. In this research, experts in Probabilistic Risk Assessment (PRA), Organizational Behavior and Information Science and Data…

How do limitations and intransparencies in data quality and data provenance bias research outcomes, and how can we detect and mitigate these limitations? For example, we have been investigating the impact of entity resolution errors on network analysis results. We found that commonly reported network metrics and derived implications can strongly deviate from the truth—as established based on…

It is difficult to understand the effectiveness of various treatment options when a huge number of external factors such as lifestyle, diet, and environment affect the burden of a disease. A major barrier to understanding is the challenge of scale—sampling enough patients to separate the major, minor, and negligible factors. With access to a database of more than one trillion public social…

INDICATOR is a novel information system for collecting, integrating, and analyzing data from multiple sources to provide public health decision makers real-time data on the health of their community. Data comes from sources as varied as emergency department visits, school attendance, veterinary clinics, and social media postings and together have been used to change public policy in outbreak…

Copyright law and resource licensing complicate the application of text data mining for research. This project convened a National Forum on Text Data Mining with Use-Limited Data in April 2018 that brought together 25 leading stakeholders selected among researchers, librarians, content providers, legal experts, and representatives of scholarly societies to articulate an agenda that provides…

How can we use user-generated content to construct, infer or refine network data? We have been tackling this problem by leveraging communication content produced and disseminated in social networks to enhance graph data. For example, we have used domain-adjusted sentiment analysis to label graphs with valence values in order to enable triadic balance assessment. The resulting method enables…

Assistant Professor Jana Diesner a received an Faculty Fellowship and seed funding for her project, “Predictive Modeling for Impact Assessment,” from the National Center for Supercomputing Applications (NCSA). Diesner collaborates closely with NCSA scientists on the project, which builds on her work developing computational solutions…

This project will develop a mobile sensor technology for performing detection and identification of viral and bacterial pathogens. By means of a smartphone-based detection instrument, the results are shared with a cloud-based data management service that will enable physicians to rapidly visualize the geographical and temporal spread of infectious disease. When deployed by a community of…

Recent research has demonstrated that investigations of contemporary societal problems can benefit from the use of long-term environmental data and from comparisons with cases in which the interactions of human societies with their environments is well-documented over centuries. By providing easy access to time- and place-specific long-term environmental data, this project seeks to facilitate…